© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36565
    Prev
    Next
    INDEX
    Explanations

    JSON.parse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    특별시
    1.55
     Vanity
    1.10
    橥
    1.09
     closes
    1.05
     Emotions
    1.03
     Delight
    1.03
     Dishes
    1.02
    ﮏ
    0.98
    そして
    0.96
     ayı
    0.96
    POSITIVE LOGITS
    us
    1.42
    ю
    1.24
    ive
    1.15
    a
    1.13
    া
    1.13
    igh
    1.11
    um
    1.09
    на
    1.09
    ude
    1.08
    TT
    1.06
    Activations Density 0.001%

    No Known Activations